%matplotlib inline

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib import cm

import ipyparallel as ipp

from time import time
from datetime import datetime

import motif as mf

from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.decomposition import PCA
from sklearn.utils import shuffle
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import roc_curve, roc_auc_score
from sklearn.model_selection import train_test_split, cross_val_score, cross_validate

from scipy.stats import spearmanr
from scipy.stats import pearsonr

Intel(R) Extension for Scikit-learn* enabled (https://github.com/intel/scikit-learn-intelex)

### set parameters for the motif analysis

PROTEIN_NAME = 'Sox10'
PROT_CONC = 0.1  # free protein concentration at binding reation; PBM typically 0.1 and RNACompete typically 0.002
BOTH_STRANDS = True  # wheter both strands are present for binding; True if double-stranded DNA or RNA is used as probes
#TIME_DISS = 1800  # experimental time span after binding reaction during which dissociation of the protein from the probe was possible

STAGES=mf.stage(protein=PROTEIN_NAME)

### read data

## RNAcompete sample data
#dfprobes_raw=pd.read_excel('./data/RNAcompete/A2BP1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/HNRNPA1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/PTBP1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/RBM24.xlsx')


#dfprobes_raw=pd.read_csv('./data/samplePBMs/Mlx__pTH2882_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Klf9__pTH2353_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Prdm11__pTH3455_HK.raw', sep='\t')
dfprobes_raw=pd.read_csv('./data/samplePBMs/Sox10__pTH1729_HK.raw', sep='\t')


print('Columns of imported Data File: %s' % dfprobes_raw.columns)
#dfprobes_raw.describe()
#dfprobes_raw.info()

Columns of imported Data File: Index(['#id_spot', 'row', 'col', 'control', 'id_probe', 'pbm_sequence',
       'linker_sequence', 'mean_signal_intensity', 'mean_background_intensity',
       'flag'],
      dtype='object')

### select columns for probe sequence and signal

column_sequence = 'pbm_sequence'
column_signal = 'mean_signal_intensity'
background_signal = 'mean_background_intensity'  #set to None if not needed
#background_signal=None

#basic preprocessing
dfprobes_raw[column_signal] = dfprobes_raw[column_signal].apply(
    lambda a: np.NaN if a == ' ' else a)
dfprobes_raw[column_signal] = dfprobes_raw[column_signal].apply(
    lambda a: np.NaN if a == '' else a)
dfprobes_raw[column_sequence] = dfprobes_raw[column_sequence].apply(
    lambda a: np.NaN if str(a).lower() == 'nan' else a)
dfprobes_raw[column_sequence] = dfprobes_raw[column_sequence].apply(
    lambda a: np.NaN if a == '' else a)
dfprobes_raw = dfprobes_raw.dropna()

#construct new dataframe with only necessary data
if type(background_signal) == type(None):
    dfprobes = pd.DataFrame({
        'seq':
        dfprobes_raw[column_sequence].astype(str),
        'signal binding':
        dfprobes_raw[column_signal].astype(np.float32)
    })  #rebuild dataframe
else:
    dfprobes = pd.DataFrame({
        'seq':
        dfprobes_raw[column_sequence].astype(str),
        'signal':
        dfprobes_raw[column_signal].astype(np.float32),
        'background':
        dfprobes_raw[background_signal].astype(np.float32)
    })  #rebuild dataframe
    dfprobes['signal binding'] = dfprobes['signal'] - dfprobes['background']

dfprobes = dfprobes.dropna()    

    
# display main properties of data set
dfprobes['signal binding'].plot(figsize=(15, 5))
dfprobes.describe()

### check type of nucleic acid

dfprobes['seq'] = dfprobes['seq'].apply(
    lambda seq: seq.upper().replace(" ", ""))  #upper and remove blanks
dfprobes['RNA'] = dfprobes['seq'].apply(
    lambda seq: all(char in 'ACGU' for char in seq))
dfprobes['DNA'] = dfprobes['seq'].apply(
    lambda seq: all(char in 'ACGT' for char in seq))
non_RNA_counts = len(dfprobes[dfprobes['RNA'] == False])
non_DNA_counts = len(dfprobes[dfprobes['DNA'] == False])

if non_RNA_counts < non_DNA_counts:
    NUC_TYPE = 'RNA'
    print('I: RNA probes detected!')
else:
    NUC_TYPE = 'DNA'
    print('I: DNA probes detected!')

if NUC_TYPE == 'RNA' and non_RNA_counts != 0:
    print(
        'E: The probe sequences appear to be RNA, however there are some non-RNA nucleotides in the sequences.'
    )
    print('E: Please check the following sequnces %s' %
          dfprobes[dfprobes['RNA'] == False])

if NUC_TYPE == 'DNA' and non_DNA_counts != 0:
    print(
        'E: The probe sequences appear to be RNA, however there are some non-RNA nucleotides in the sequences.'
    )
    print('E: Please check the following sequnces %s' %
          dfprobes[dfprobes['DNA'] == False])

I: DNA probes detected!

### option to add a constant sequence at the 3' end and 5' end
sequence_to_be_added_5 = ''
sequence_to_be_added_3 = 'CCTGT'  # standard PBM arrays: CCTGTGTGAAATTGTTATCCGCTCT T7 array: GTCTTGA..
dfprobes['seq'] = sequence_to_be_added_5.upper(
) + dfprobes['seq'] + sequence_to_be_added_3.upper()
print(
    f"I: The nucleotide sequence {sequence_to_be_added_5.upper()} has been added to the 5' end all probe sequences."
)
print(
    f"I: The nucleotide sequence {sequence_to_be_added_3.upper()} has been added to the 3' end all probe sequences."
)

I: The nucleotide sequence  has been added to the 5' end all probe sequences.
I: The nucleotide sequence CCTGT has been added to the 3' end all probe sequences.

### egalize length
dfprobes['seq_length'] = dfprobes['seq'].apply(len)

if max(dfprobes['seq_length']) != min(dfprobes['seq_length']):
    print('I: Probes length is not uniform, detected range: %i ..%i' %
          (min(dfprobes['seq_length']), max(dfprobes['seq_length'])))
    max_length = max(dfprobes['seq_length'])
    dfprobes['padded_sequence'] = dfprobes['seq'].apply(
        lambda seq: seq + ((max_length - len(seq)) * '-'))
    print(
        "I: Probe sequences have been padded at the 5' to the uniform length of %i nucleotides"
        % max_length)
else:
    print('I: Probe sequences have the uniform length of %i nucleotides' %
          (dfprobes['seq_length'].median()))
    dfprobes['padded_sequence'] = dfprobes['seq']

print('I: Total datasets contains %i sequences.' % len(dfprobes))

# visualize composition of each position
df_nucleotides = mf.split_sequence_in_nucleotides(dfprobes['padded_sequence'])
dfcount = pd.DataFrame(index=['A', 'C', 'G', 'T', 'U', '-'])
for column in df_nucleotides:
    dfcount[column] = df_nucleotides[column].value_counts()
dfcount = dfcount.fillna(0)  #zeros for NaN
dfcount.transpose().plot(figsize=(15, 5), kind='bar')
print('I: Visualisation of the base composition per position')
print(
    'I: If positions are invariant they can be removed before sequence analysis.'
)

I: Probes length is not uniform, detected range: 36 ..40
I: Probe sequences have been padded at the 5' to the uniform length of 40 nucleotides
I: Total datasets contains 40330 sequences.
I: Visualisation of the base composition per position
I: If positions are invariant they can be removed before sequence analysis.

# You may remove invariant continuos positions by adjusting the slicing.
# It is recommended to leave a few invariant positions to allow for binding events
# between the variable and constant part of the probes.

dfprobes['padded_sequence'] = dfprobes['padded_sequence'].apply(lambda s: s[:])  ### <==== do the slicing here

# visualize composition of each position
print('I: Visualisation of the base composition per position after slicing.')
df_nucleotides = mf.split_sequence_in_nucleotides(dfprobes['padded_sequence'])
dfcount = pd.DataFrame(index=['A', 'C', 'G', 'T', 'U', '-'])
for column in df_nucleotides:
    dfcount[column] = df_nucleotides[column].value_counts()
dfcount = dfcount.fillna(0)  #zeros for NaN
dfcount.transpose().plot(figsize=(15, 5), kind='bar')
plt.show()

# preparation for later classification
mean = dfprobes['signal binding'].mean()
std = dfprobes['signal binding'].std()
THRESHOLD = mean + 4 * std  #4*std used according to Weirauch et al., 2013
dfprobes['positive probe'] = dfprobes['signal binding'].apply(
    lambda s: True if s > THRESHOLD else False)

print(
    'I: The whole dataset has been used to set the threshold for a positive probe.'
)
print('I: The threshold is %f' % THRESHOLD)
print(
    f"I: {len(dfprobes[dfprobes['positive probe']])} probes of {len(dfprobes)} are above threshold."
)

if len(dfprobes[dfprobes['positive probe']]) == 0:
    print(
        'E: No probe above THRESHOLD. Classification is not possible. Please adjust the THRESHOLD.'
    )

I: Visualisation of the base composition per position after slicing.

I: The whole dataset has been used to set the threshold for a positive probe.
I: The threshold is 5786.895752
I: 342 probes of 40330 are above threshold.

#### Shuffle and prepare dataset for training and testing

# shuffle and split
dfprobes = shuffle(dfprobes)
dftrain, dftest = train_test_split(dfprobes, test_size=0.2)

print(
    'I: The whole dataset has been split in training (80%) and test (20%) datasets.'
)

# display histogramms of test and training set
dftrain['signal binding'].plot(kind='hist', bins=25).axvline(x=THRESHOLD, color='r', linestyle='-.', lw=0.5, label='threshold classification')
dftest['signal binding'].plot(kind='hist', bins=25)
plt.show()

# generate a subset with maximal 1000 probes

downsampled_size = 1000  # You may change downsampled size here.

percentile = 0.5 * downsampled_size / len(
    dftrain
) * 100  #percentile required for lowest and highest to achieve down-sampled size
if percentile < 4:
    percentile = 4  #do not use only the extreme values
elif percentile > 10:
    percentile = 10  #avoid taking value from the mid-range

if len(dftrain) * percentile * 2 / 100 < downsampled_size / 4:
    print('W: The subset only contains %i probes - a rather low number.' %
          dftrain * percentile * 2 / 100)

print(
    'I: A downsampled dataset containing the lowest and highest %.1f %% of the dataset is generated.'
    % percentile)
dfsubset_high = dftrain[dftrain['signal binding'] >= dftrain['signal binding'].quantile(1 - percentile / 100)]  # highest part
dfsubset_low = dftrain[dftrain['signal binding'] <= dftrain['signal binding'].quantile(percentile / 100)]  # lowest part
print('I: Median values of lowest and highest %.1f %%:  %r  %r' %
      (percentile, dfsubset_low['signal binding'].quantile(0.5),
       dfsubset_high['signal binding'].quantile(0.5)))

if len(dfsubset_high) + len(dfsubset_low) > downsampled_size:
    print('I: The dataset is further downsampled to %i sequences.' %
          downsampled_size)
    dfsubset_high = dfsubset_high.sample(downsampled_size - int(downsampled_size / 2))
    dfsubset_low = dfsubset_low.sample(int(downsampled_size / 2))
    dfsubset = pd.concat([dfsubset_high, dfsubset_low])
else:
    dfsubset = pd.concat([dfsubset_high, dfsubset_low])

dfsubset = shuffle(dfsubset)   
    
# display main properties of downsampled data set
print('I: Histogramm of the downsampled dataset along the with classification threshold.')
dfsubset['signal binding'].plot(kind='hist', bins=25).axvline(x=THRESHOLD, color='r', linestyle='-.', lw=0.5, label='threshold classification')
plt.show()

# establish numpy arrays of the sequenc and binding data in the dataframes

# complete data
X=mf.hotencode_sequence(dfprobes['padded_sequence'], nuc_type=NUC_TYPE)
y=np.array(dfprobes['signal binding'])

# training set
X_train=mf.hotencode_sequence(dftrain['padded_sequence'], nuc_type=NUC_TYPE)
y_train=np.array(dftrain['signal binding'])

# subset of training set
X_subset=mf.hotencode_sequence(dfsubset['padded_sequence'], nuc_type=NUC_TYPE)
y_subset=np.array(dfsubset['signal binding'])

# test set
X_test=mf.hotencode_sequence(dftest['padded_sequence'], nuc_type=NUC_TYPE)
y_test=np.array(dftest['signal binding'])

I: The whole dataset has been split in training (80%) and test (20%) datasets.

I: A downsampled dataset containing the lowest and highest 4.0 % of the dataset is generated.
I: Median values of lowest and highest 4.0 %:  10.22979736328125  4106.89892578125
I: The dataset is further downsampled to 1000 sequences.
I: Histogramm of the downsampled dataset along the with classification threshold.

### perform a quick & dirty round for a short motif by fitting on subset to check data integrity

#fit regression quick_model
quick_model=mf.findmotif(motif_length=3, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS, ftol=0.01)

start = time()
quick_model.fit(X_subset,y_subset)
print("I: Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
quick_model.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('quick', quick_model)
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Optimization took 0.02 hours.
I: energy matrix and logos:

        A     C      G      T
0  15189  1490   1051 -17731
1   1533   566  10875 -12975
2 -12388 -2623  -2576  17587

I: summed absolute energies of each position:
0    35463
1    25950
2    35175
dtype: int64

I: averaged summed energy over all positions: 32196
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -5376 +/- 19332
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.31631 .. 9.45840 (ratio: 29.9)
I: number of probes: 1000
I: Pearson Correlation  r: 0.3460
I: mean absolute error: 2202.4280

I: Classification performance AUROC: 0.6343

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed

#### Perfrom GridCV Search for exploration of the motif length goal: identify the minimum motif length which gives a good r-value

# optional: allow for global optimization to verify whether the local optimization is good enough
# not recommended include fitG0=True. This option should only be considered when the local optimization is started with an approximate motif and the start parameter is set
# not recommended set time_dissociation. The effect of dissociation should be only considered when the local optimization is started with an approximate motif.


# prepare grid search over motif_length
model_grid=mf.findmotif(protein_conc=PROT_CONC, both_strands=BOTH_STRANDS)
param_grid = {"motif_length": [3,4,5,6,7,8]}     # choose sensible range for length of motif

# define custom refit function
def custom_refit(cv_results):
    """returns index of max r2/sqrt(motif_length)"""
    df_grid=pd.DataFrame(cv_results)
    index=(df_grid['mean_test_score']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))).idxmax()
    return index

# run grid search and refit according to custom refit
grid_search = GridSearchCV(model_grid, param_grid=param_grid, verbose=2, cv=5, refit=custom_refit, n_jobs=-1)

start = time()
grid_search.fit(X_subset, y_subset)

print("I: GridSearchCV took %.2f hours for %d candidate parameter settings."
    % ((time() - start)/3600, len(grid_search.cv_results_["params"])))
print('I: number of samples: %i' %len(X_subset))

df_grid=pd.DataFrame(grid_search.cv_results_)
print('I: Plot of r2 vs motif length and vs root(motif length)')
df_grid.rename(columns={'mean_test_score':'r2'}, inplace=True)
df_grid.plot(kind='scatter', x='param_motif_length', y='r2', yerr='std_test_score', figsize=(5,3)).set_xticks(param_grid["motif_length"])
df_grid['r2/sqrt(length)']=df_grid['r2']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))
df_grid['std/sqrt(length)']=df_grid['std_test_score']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))
df_grid.plot(kind='scatter', x='param_motif_length', y='r2/sqrt(length)',yerr='std/sqrt(length)', figsize=(5,3)).set_xticks(param_grid["motif_length"])
plt.show()

best_index=df_grid['r2/sqrt(length)'].idxmax()
CORE_MOTIF_LENGTH=df_grid.loc[best_index, 'param_motif_length']
print(f'I: The maximum ({CORE_MOTIF_LENGTH}) is suggested as CORE_MOTIF_LENGTH')

print('I: motif obtained with the best estimator from gridCV search')
# print & display results from best estimator
model_grid=grid_search.best_estimator_
model_grid.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('best grid', model_grid)
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

Fitting 5 folds for each of 6 candidates, totalling 30 fits
I: GridSearchCV took 1.76 hours for 6 candidate parameter settings.
I: number of samples: 1000
I: Plot of r2 vs motif length and vs root(motif length)

I: The maximum (5) is suggested as CORE_MOTIF_LENGTH
I: motif obtained with the best estimator from gridCV search
I: energy matrix and logos:

       A      C     G      T
0   118   7141 -1458  -5801
1  6308  10161 -6016 -10453
2 -2953  -3615 -4508  11077
3 -3295   2313  5123  -4141
4   333    130  1470  -1934

I: summed absolute energies of each position:
0    14519
1    32939
2    22155
3    14874
4     3869
dtype: int64

I: averaged summed energy over all positions: 17671
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -2166 +/- 12995
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00242 .. 0.13354 (ratio: 55.2)
I: number of probes: 1000
I: Pearson Correlation  r: 0.4821
I: mean absolute error: 1997.6874

I: Classification performance AUROC: 0.7410

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed
1	best grid	Sox10	1000	5	0.482118	0.740957	-4780.494388	False	55.233242	0.133535	0.002418	118,..	suppressed

### run a number of identical optimizations with motif length found during grid search
### goal: find best motif through repetition, judge stabiltiy of optimization

#CORE_MOTIF_LENGTH=5  # adjust core motif length if needed, motif length can be changed later

# prepare for ipyparallel
number_of_optimizations = 20
model_list = [mf.findmotif(motif_length=CORE_MOTIF_LENGTH, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS)] * number_of_optimizations
X_list = [X_subset] * number_of_optimizations
y_list = [y_subset] * number_of_optimizations


def single_job(model, X, y):
    model.fit(X, y)
    return {'model':model}

# run the optimizations on ipp.cluster
start = time()
with ipp.Cluster(log_level=40) as rc:
    rc[:].use_pickle()
    view = rc.load_balanced_view()
    asyncresult = view.map_async(single_job, model_list, X_list, y_list)
    asyncresult.wait_interactive()
    result = asyncresult.get()
print("I: Optimization took %.2f hours." % ((time() - start) / 3600))


  
# assemble results and analyze
df_repetitions=pd.DataFrame(result)
df_repetitions['r (subset)']=df_repetitions['model'].apply(lambda e: e.rvalue)
df_repetitions['r (train)']=df_repetitions['model'].apply(lambda e: mf.linregress(e.predict(X_train),y_train).rvalue)
df_repetitions['r (test)']=df_repetitions['model'].apply(lambda e: mf.linregress(e.predict(X_test),y_test).rvalue)
df_repetitions['G0']=df_repetitions['model'].apply(lambda e: e.finalG0_)
df_repetitions['max binding']=df_repetitions['model'].apply(lambda e: e.max_binding_fit)
df_repetitions['min binding']=df_repetitions['model'].apply(lambda e: e.min_binding_fit)
df_repetitions['ratio'] = df_repetitions['model'].apply(lambda e: e.ratio)
df_repetitions['energies']=df_repetitions['model'].apply(lambda e: e.energies_)
#df_repetitions['information']=df_repetitions['model'].apply(lambda e: mf.energies2information(e.energies_))


# display results of the ensemble of optimizations
print('I: Results of the repeated motif finding, sorted according to the regression coefficient with the train dataset')
df_repetitions.sort_values('r (train)', ascending=False, inplace=True)
mf.display_df(df_repetitions, nuc_type=NUC_TYPE)

  0%|          | 0/16 [00:00<?, ?engine/s]

single_job:   0%|          | 0/20 [00:00<?, ?tasks/s]

I: Optimization took 0.54 hours.
I: Results of the repeated motif finding, sorted according to the regression coefficient with the train dataset

	model	r (subset)	r (train)	r (test)	G0	max binding	min binding	ratio	energies	logo
14	suppressed	0.542537	0.418947	0.425094	-4780.494388	0.133775	0.000482	277.682858	-8342,..
8	suppressed	0.542870	0.418309	0.423895	-4780.494388	0.288288	0.000522	551.839391	-6697,..
13	suppressed	0.542834	0.417885	0.424621	-4780.494388	0.083920	0.000332	253.036200	-5407,..
11	suppressed	0.543285	0.416326	0.421527	-4780.494388	0.190321	0.000959	198.392736	-4014,..
1	suppressed	0.537783	0.408618	0.407603	-4780.494388	0.254099	0.000771	329.480480	-7214,..
9	suppressed	0.537237	0.407536	0.406698	-4780.494388	0.243159	0.000778	312.587260	-6778,..
4	suppressed	0.491033	0.361908	0.369656	-4780.494388	8.206595	0.001150	7136.348345	-12625,..
15	suppressed	0.484738	0.348589	0.366206	-4780.494388	0.069451	0.002042	34.006610	2153,..
6	suppressed	0.484760	0.347083	0.362969	-4780.494388	0.211545	0.006157	34.360060	2859,..
17	suppressed	0.484288	0.346023	0.362497	-4780.494388	0.259120	0.005650	45.857935	2181,..
2	suppressed	0.484382	0.345964	0.361844	-4780.494388	0.033783	0.000861	39.245147	2325,..
18	suppressed	0.483520	0.339085	0.352717	-4780.494388	0.264939	0.006292	42.105255	7675,..
7	suppressed	0.483267	0.338943	0.352321	-4780.494388	0.195463	0.004895	39.931855	7710,..
10	suppressed	0.482704	0.338241	0.351313	-4780.494388	0.277541	0.006050	45.876489	15293,..
3	suppressed	0.388591	0.332517	0.338434	-4780.494388	17.159354	0.012353	1389.132342	-16360,..
19	suppressed	0.445382	0.321095	0.329786	-4780.494388	7.673333	0.011667	657.670511	5152,..
0	suppressed	0.445400	0.321048	0.330323	-4780.494388	7.705063	0.012391	621.815094	4856,..
5	suppressed	0.430979	0.309843	0.328319	-4780.494388	9.092000	0.013397	678.680447	11256,..
12	suppressed	0.392863	0.281105	0.286212	-4780.494388	8.543554	0.045869	186.258909	-12214,..
16	suppressed	0.293695	0.259328	0.267340	-4780.494388	5.806181	0.018451	314.680670	3188,..

### compare energy matrices of ensemble using PCA
print('I: Histogram of the regression coefficients r obtained by repeated optimizaion with the subset.')
df_repetitions['r (subset)'].plot(kind='hist')
plt.show()

pca = PCA(n_components=2)
pca_2c=pca.fit_transform(df_repetitions['energies'].tolist())    
df_repetitions[['PCA1', 'PCA2']]=pca_2c

if sum(pca.explained_variance_ratio_)<0.5:
      print('W: 2-dimensional PCA explained only %i %% of variance' %(sum(pca.explained_variance_ratio_)*100))
else:
    print('I: 2-dimensional PCA explained %i %% of variance.' %(sum(pca.explained_variance_ratio_)*100))
print('I: Visualization of the PCA with the regression quality vs. subset and training dataset by color.')        
df_repetitions.plot(x='PCA1', y='PCA2', kind='scatter', c='r (subset)',cmap=cm.coolwarm, edgecolors='black', linewidths=0.3)
df_repetitions.plot(x='PCA1', y='PCA2', kind='scatter', c='r (train)',cmap=cm.coolwarm, edgecolors='black', linewidths=0.3)

I: Histogram of the regression coefficients r obtained by repeated optimizaion with the subset.

I: 2-dimensional PCA explained 72 % of variance.
I: Visualization of the PCA with the regression quality vs. subset and training dataset by color.

/home/GLipps/.local/lib/python3.8/site-packages/sklearn/utils/deprecation.py:101: FutureWarning: Attribute `n_features_` was deprecated in version 1.2 and will be removed in 1.4. Use `n_features_in_` instead.
  warnings.warn(msg, category=FutureWarning)

<matplotlib.axes._subplots.AxesSubplot at 0x7fb7dbb24f40>

# visualisation of the motif with the highest r with the train dataset
print('I: Best motif according to r (train) from the repeated optimizations.')
print('I: PCA components: %i, %i' %(df_repetitions.iloc[0]['PCA1'], df_repetitions.iloc[0]['PCA2']))
model_best_repetition=df_repetitions.iloc[0]['model']
model_best_repetition.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE) 
# store results and display stages
STAGES.append('best repetition', model_best_repetition, new_entries={'r (test)': mf.linregress(model_best_repetition.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Best motif according to r (train) from the repeated optimizations.
I: PCA components: -16441, 8389
I: energy matrix and logos:

       A      C     G     T
0 -8342  17137 -4652 -4141
1  2758    862  3088 -6709
2  4296   3478 -1655 -6120
3  -458  -1041 -1887  3386
4 -2945   2974  3715 -3744

I: summed absolute energies of each position:
0    34274
1    13418
2    15551
3     6773
4    13380
dtype: int64

I: averaged summed energy over all positions: 16679
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -2831 +/- 12315
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00048 .. 0.13377 (ratio: 277.7)
I: number of probes: 1000
I: Pearson Correlation  r: 0.5425
I: mean absolute error: 1871.2741

I: Classification performance AUROC: 0.7736

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed		NaN
1	best grid	Sox10	1000	5	0.482118	0.740957	-4780.494388	False	55.233242	0.133535	0.002418	118,..	suppressed		NaN
2	best repetition	Sox10	1000	5	0.542537	0.773596	-4780.494388	False	277.682858	0.133775	0.000482	-8342,..	suppressed		0.425094

### motif finding on complete training dataset starting with best motif from repetitions

#fit & predict optimization starting with previous energy matrix
model_train=mf.findmotif(motif_length=CORE_MOTIF_LENGTH, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=model_best_repetition.energies_)
start = time()
model_train.fit(X_train,y_train)
print("I: Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
model_train.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('train dataset', model_train, new_entries={'r (test)': mf.linregress(model_train.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Optimization took 6.91 hours.
I: energy matrix and logos:

       A      C     G     T
0 -7741  17101 -4607 -4752
1  1051    684  1731 -3467
2   479   2596  1036 -4113
3  -418    115 -2563  2866
4 -2017   1150  4098 -3231

I: summed absolute energies of each position:
0    34203
1     6934
2     8226
3     5963
4    10497
dtype: int64

I: averaged summed energy over all positions: 13165
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -2109 +/- 11050
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00014 .. 0.01280 (ratio: 93.6)
I: number of probes: 32264
I: Pearson Correlation  r: 0.4469
I: mean absolute error: 558.1037

I: Classification performance AUROC: 0.8913

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed		NaN
1	best grid	Sox10	1000	5	0.482118	0.740957	-4780.494388	False	55.233242	0.133535	0.002418	118,..	suppressed		NaN
2	best repetition	Sox10	1000	5	0.542537	0.773596	-4780.494388	False	277.682858	0.133775	0.000482	-8342,..	suppressed		0.425094
3	train dataset	Sox10	32264	5	0.446872	0.891277	-4780.494388	False	93.611628	0.012801	0.000137	-7741,..	suppressed		0.460862

### Based on the motif of CORE_MOTIF_LENGTH analyze the neigbouring positions 
### whether their inclusion can improve the quality of the motif
df_positions=model_train.investigate_extension_parallel(X_train,y_train, end5=3, end3=3, nuc_type=NUC_TYPE)

list_positions=df_positions.index[df_positions['+2%']].tolist()+[0] # list of positions with an increase of2% and default position 0
ext5=-min(list_positions)
ext3=max(list_positions)
print("I: It is suggested to extend the core motif at the 5' end by %i and at the 3' end by %i positions." %(ext5, ext3))

### Analyze model whether the estimated G0 is correct
df_G0=model_train.investigate_G0(X_train,y_train)

  0%|          | 0/6 [00:00<?, ?engine/s]

job5:   0%|          | 0/3 [00:00<?, ?tasks/s]

job3:   0%|          | 0/3 [00:00<?, ?tasks/s]

I: Optimization took 0.45 hours.

I: It is suggested to extend the core motif at the 5' end by 0 and at the 3' end by 1 positions.
I: Current G0 = -4780 J/mol (see red broken line in figure below) with r = 0.447.
I: Maximal r is 0.447 at G0=24220 J/mol (see green broken line below).
I: Maximal occupancy of 2 is reached at G0=-17780 J/mol (see blue broken line below).
I: Maximal occupancy of 0.2 is reached at G0=-11780 J/mol (see blue broken line below).

W: Current G0 leads to a maximal probe occupancy below 0.2. G0 can be manuylly set and be decreased.
I: Maximal r is close to r achieved with current G0. Good.

### fit & predict optimization starting with extended energy matrix if extension appears to improve prediction

if ext5+ext3!=0: #extension suggestion from previous analysis of the bordering positions
    expanded_energies=model_train.energies_
    # append energies of single-optimized bordering positions to energies of central part
    if ext5!=0:
        energies_5=np.concatenate(df_positions['energies'][(df_positions.index<0) & (df_positions.index>=-ext5)].to_numpy())
        expanded_energies=np.concatenate((energies_5, expanded_energies))
    if ext3!=0:
        energies_3=np.concatenate(df_positions['energies'][(df_positions.index<=ext3) & (df_positions.index>0)].to_numpy().flatten())
        expanded_energies=np.concatenate((expanded_energies,  energies_3))

    mf.energies2logo(expanded_energies, nuc_type=NUC_TYPE)
    print('I: Optimization started with extended motif.')
    expanded_motif_length=len(expanded_energies)//4
    
    
    model_extended=mf.findmotif(motif_length=expanded_motif_length, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=expanded_energies)

    start = time()
    model_extended.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    model_extended.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

    # store results and display stages
    STAGES.append('train, extended', model_extended, new_entries={'r (test)': mf.linregress(model_extended.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)
else:
    model_extended=model_train
    print('I: Motif is not extended based on previous analysis.')

I: Optimization started with extended motif.
Optimization took 4.99 hours.
I: energy matrix and logos:

       A      C     G     T
0 -8262  17412 -4309 -4840
1  3050    554   533 -4138
2  -288   3739  1363 -4814
3   -25   -157 -2642  2824
4 -2069   1849  3424 -3204
5   235    604   868 -1707

I: summed absolute energies of each position:
0    34824
1     8276
2    10206
3     5649
4    10547
5     3415
dtype: int64

I: averaged summed energy over all positions: 12153
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -803 +/- 11460
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00004 .. 0.01167 (ratio: 264.1)
I: number of probes: 32264
I: Pearson Correlation  r: 0.4840
I: mean absolute error: 552.1083

I: Classification performance AUROC: 0.9194

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed		NaN
1	best grid	Sox10	1000	5	0.482118	0.740957	-4780.494388	False	55.233242	0.133535	0.002418	118,..	suppressed		NaN
2	best repetition	Sox10	1000	5	0.542537	0.773596	-4780.494388	False	277.682858	0.133775	0.000482	-8342,..	suppressed		0.425094
3	train dataset	Sox10	32264	5	0.446872	0.891277	-4780.494388	False	93.611628	0.012801	0.000137	-7741,..	suppressed		0.460862
4	train, extended	Sox10	32264	6	0.484036	0.919414	-1946.454775	False	264.131799	0.011667	0.000044	-8262,..	suppressed		0.487629

### fit & predict optimization starting with extended energy matrix plus one bordering position on each side if current bordering position exceed the information of 0.25

I_5=mf.energies2information(model_extended.energies_[0:4])>=0.25 #sufficient information content of 5' end position
I_3=mf.energies2information(model_extended.energies_[-4:])>=0.25 #sufficient information content of 3' end position

if I_5 or I_3:
    print('I: At least one of the bordering positions has an information content of at least 0.25. Extending.')
    expanded_energies_with_border=mf.modify_energies(model_extended.energies_, end5=I_5, end3=I_3)  
    mf.energies2logo(expanded_energies_with_border, nuc_type=NUC_TYPE)
    motif_length_with_border=len(expanded_energies_with_border)//4

    model_with_border=mf.findmotif(motif_length=motif_length_with_border, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=expanded_energies_with_border)


    start = time()
    model_with_border.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    model_with_border.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

    # store results and display stages
    STAGES.append('train, expanded, border', model_with_border, new_entries={'r (test)': mf.linregress(model_with_border.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)
else:
    print('I: Both bordering positions of the found motif have an information content below 0.25. No futher optimization required.')

I: At least one of the bordering positions has an information content of at least 0.25. Extending.

Optimization took 4.99 hours.
I: energy matrix and logos:

       A      C     G     T
0   -26   -621  1209  -560
1 -8108  17282 -4454 -4719
2  3415    437   387 -4240
3    73   2940  1293 -4307
4  -107    -15 -2637  2760
5 -2075   2042  3209 -3176
6   180    554   913 -1648

I: summed absolute energies of each position:
0     2418
1    34565
2     8480
3     8614
4     5520
5    10502
6     3296
dtype: int64

I: averaged summed energy over all positions: 10485
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: 609 +/- 11370
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00001 .. 0.00362 (ratio: 242.2)
I: number of probes: 32264
I: Pearson Correlation  r: 0.4759
I: mean absolute error: 550.2746

I: Classification performance AUROC: 0.8831

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed		NaN
1	best grid	Sox10	1000	5	0.482118	0.740957	-4780.494388	False	55.233242	0.133535	0.002418	118,..	suppressed		NaN
2	best repetition	Sox10	1000	5	0.542537	0.773596	-4780.494388	False	277.682858	0.133775	0.000482	-8342,..	suppressed		0.425094
3	train dataset	Sox10	32264	5	0.446872	0.891277	-4780.494388	False	93.611628	0.012801	0.000137	-7741,..	suppressed		0.460862
4	train, extended	Sox10	32264	6	0.484036	0.919414	-1946.454775	False	264.131799	0.011667	0.000044	-8262,..	suppressed		0.487629
5	train, expanded, border	Sox10	32264	7	0.475891	0.883061	659.713619	False	242.192738	0.003621	0.000015	-26,..	suppressed		0.477905

### Analyze model whether the estimated G0 is correct
df_G0=model_extended.investigate_G0(X_train,y_train)

I: Current G0 = -1946 J/mol (see red broken line in figure below) with r = 0.484.
I: Maximal r is 0.484 at G0=27054 J/mol (see green broken line below).
I: Maximal occupancy of 2 is reached at G0=-15946 J/mol (see blue broken line below).
I: Maximal occupancy of 0.2 is reached at G0=-8946 J/mol (see blue broken line below).

W: Current G0 leads to a maximal probe occupancy below 0.2. G0 can be manuylly set and be decreased.
I: Maximal r is close to r achieved with current G0. Good.

### optional adjustment of GO

G0=-8000   # <==== adjust G0 manually here

last_model=STAGES.df.at[max(STAGES.df.index),'model']
last_model.G0=G0

start = time()
last_model.fit(X_train,y_train)
print("Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
last_model.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('manually adjusted G0', last_model, new_entries={'r (test)': mf.linregress(last_model.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

Optimization took 5.08 hours.
I: energy matrix and logos:

       A      C     G     T
0   -72   -624  1247  -550
1 -8073  17123 -4398 -4650
2  3257    499   439 -4196
3    52   2914  1334 -4301
4   -80    -17 -2661  2760
5 -2063   2005  3222 -3164
6   191    564   915 -1670

I: summed absolute energies of each position:
0     2494
1    34246
2     8393
3     8602
4     5520
5    10455
6     3341
dtype: int64

I: averaged summed energy over all positions: 10436
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -3722 +/- 11849
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00048 .. 0.11181 (ratio: 233.7)
I: number of probes: 32264
I: Pearson Correlation  r: 0.4753
I: mean absolute error: 550.3820

I: Classification performance AUROC: 0.8831

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Sox10	1000	3	0.345967	0.634327	-11473.366709	False	29.902698	9.458397	0.316306	15189,..	suppressed		NaN
1	best grid	Sox10	1000	5	0.482118	0.740957	-4780.494388	False	55.233242	0.133535	0.002418	118,..	suppressed		NaN
2	best repetition	Sox10	1000	5	0.542537	0.773596	-4780.494388	False	277.682858	0.133775	0.000482	-8342,..	suppressed		0.425094
3	train dataset	Sox10	32264	5	0.446872	0.891277	-4780.494388	False	93.611628	0.012801	0.000137	-7741,..	suppressed		0.460862
4	train, extended	Sox10	32264	6	0.484036	0.919414	-1946.454775	False	264.131799	0.011667	0.000044	-8262,..	suppressed		0.487629
5	train, expanded, border	Sox10	32264	7	0.475891	0.883061	659.713619	False	242.192738	0.003621	0.000015	-26,..	suppressed		0.477905
6	manually adjusted G0	Sox10	32264	7	0.475340	0.883072	-8000.000000	False	233.685311	0.111809	0.000478	-72,..	suppressed		0.476838

STAGES.df.to_json('%s_%s-%s-%s_%s-%s.json' %(PROTEIN_NAME, datetime.now().year, datetime.now().month,datetime.now().day , datetime.now().hour, datetime.now().minute))
STAGES.df.to_pickle('%s_%s-%s-%s_%s-%s.pkl' %(PROTEIN_NAME, datetime.now().year, datetime.now().month,datetime.now().day , datetime.now().hour, datetime.now().minute))

mf.energies2logo(mf.reverse_complement(STAGES.df.at[4,'energies']), nuc_type=NUC_TYPE)

	A	C	G	T
0	-1707.634453	868.504919	604.107498	235.022037
1	-3204.219750	3424.141738	1849.612202	-2069.534190
2	2824.819967	-2642.288381	-157.442873	-25.088713
3	-4814.689908	1363.719431	3739.368461	-288.397984
4	-4138.256957	533.551437	554.216718	3050.488803
5	-4840.750912	-4309.319943	17412.123879	-8262.053024